CN109961791A - A kind of voice information processing method, device and electronic equipment - Google Patents
A kind of voice information processing method, device and electronic equipment Download PDFInfo
- Publication number
- CN109961791A CN109961791A CN201711404260.5A CN201711404260A CN109961791A CN 109961791 A CN109961791 A CN 109961791A CN 201711404260 A CN201711404260 A CN 201711404260A CN 109961791 A CN109961791 A CN 109961791A
- Authority
- CN
- China
- Prior art keywords
- character string
- user
- language character
- word
- language
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000010365 information processing Effects 0.000 title claims abstract description 19
- 238000003672 processing method Methods 0.000 title claims abstract description 15
- 238000000034 method Methods 0.000 claims abstract description 48
- 238000005457 optimization Methods 0.000 claims abstract description 14
- 230000011218 segmentation Effects 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 description 13
- 238000009835 boiling Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 238000010276 construction Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 230000003993 interaction Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000000712 assembly Effects 0.000 description 2
- 238000000429 assembly Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- 241000039077 Copula Species 0.000 description 1
- 206010052804 Drug tolerance Diseases 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000026781 habituation Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Acoustics & Sound (AREA)
- Human Computer Interaction (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses a kind of voice information processing method, device and electronic equipments.The voice information processing method includes: acquisition voice messaging；Speech recognition is carried out to voice messaging, obtains the corresponding language character string of voice messaging；According to the personalized character database of user in input method, the language character string after being optimized is optimized to language character string.In the above-mentioned technical solutions, the result of speech recognition is optimized by the personalized character database of user, the personalized character input situation of the more accurate reflection user of the result after the optimization enable, to improve the accuracy rate of speech recognition.
Description
Technical field
The present invention relates to voice technology field, in particular to a kind of voice information processing method, device and electronic equipment.
Background technique
With the continuous development of science and technology, voice technology has obtained development at full speed, and the accuracy rate of speech recognition is continuous
It improves, is gradually expanding in the application of field of human-computer interaction.Nowadays, speech recognition has been able to identify that user is defeated well
The voice messaging that enters simultaneously is converted into language and characters character, realizes that voice inputs text.
Nowadays, the accuracy rate of speech recognition has been able to reach 90% or more, and the database of speech recognition is suitable
It is perfect, to further increase the accuracy rate of speech recognition, need a kind of new method and start with from other aspects to optimize
The result of speech recognition.
Summary of the invention
The embodiment of the present invention provides a kind of voice information processing method, device and electronic equipment, for improving speech recognition
Accuracy rate.
In a first aspect, the embodiment of the present invention provides a kind of voice information processing method, this method comprises:
Obtain voice messaging；
Speech recognition is carried out to the voice messaging, obtains the corresponding language character string of the voice messaging；
According to the personalized character database of user in input method, the language character string is optimized after being optimized
Language character string.
Optionally, which comprises obtain the name and/place name that user inputs in default application program；According to institute
Name and/or place name are stated, the personalized character database is establishd or updated.
Optionally, which comprises it obtains the user and passes through the fuzzy phoneme word shielded in input method, and/or, obtain institute
It states user and inputs the high frequency words that number is greater than the first given threshold in preset period of time；According to the fuzzy phoneme word and/or institute
High frequency words are stated, the personalized character database is establishd or updated.
Optionally, which comprises obtain N number of input word that user continuously inputs, N is the integer more than or equal to two；
Judge whether the input number of N number of input word is greater than the second given threshold；If so, being closed N number of input word as N member
Copula, and the personalized character database is establishd or updated according to the N member relative.
Optionally, according to the personalized character database of user in input method, the language character string is optimized and is obtained
Language character string after must optimizing, comprising:
The language character string is segmented；
Judge in the personalized character database with the presence or absence of same or similar with participle pronunciation any in word segmentation result
Target word；
The target word if it exists corresponding participle will replace with after the target word optimized in the language character string
Language character string.
Optionally, the target word if it exists corresponding participle will replace with the target word and obtain in the language character string
Language character string after must optimizing, comprising:
The target word if it exists judges the adjacent participle of the target word with participle to be replaced in the language character string
Between whether there is N member relationship, wherein participle to be replaced is that pronunciation is identical as the target word or phase in the language character string
Close participle；
Participle to be replaced described in the language character string is replaced with the target word and obtained by the N member relationship if it exists
Language character string after must optimizing.
Optionally, the target word if it exists corresponding participle will replace with the target word and obtain in the language character string
Language character string after must optimizing, comprising:
The target word if it exists judges whether the target word is name, place name or fuzzy phoneme word；
If so, participle corresponding in the language character string is replaced with the language character after the target word is optimized
String.
Second aspect, the embodiment of the present invention provide a kind of speech information processing apparatus, comprising:
Acquiring unit obtains voice messaging；
Recognition unit carries out speech recognition to the voice messaging, obtains the corresponding language character string of the voice messaging；
Optimize unit, for the personalized character database according to user in input method, the language character string is carried out
Language character string after being optimized.
Optionally, described device further include: construction unit, the name inputted in default application program for obtaining user
With/place name；According to the name and/or place name, the personalized character database is establishd or updated.
Optionally, described device further include: construction unit passes through the fuzzy phoneme shielded in input method for obtaining the user
Word, and/or, it obtains the user and inputs the high frequency words that number is greater than the first given threshold in preset period of time；According to institute
Fuzzy phoneme word and/or the high frequency words are stated, the personalized character database is establishd or updated.
Optionally, described device further include: construction unit, the N number of input word continuously inputted for obtaining user, N is big
In the integer for being equal to two；Judge whether the input number of N number of input word is greater than the second given threshold；If so, by described N number of
Input word establishs or updates the personalized character database as N member relative, and according to the N member relative.
Optionally, the optimization unit, comprising: word segmentation module, for being segmented to the language character string；Judge mould
Block, for judging in the personalized character database with the presence or absence of same or similar with participle pronunciation any in word segmentation result
Target word；Participle corresponding in the language character string is replaced with the target for the target word if it exists by replacement module
Word optimized after language character string.
Optionally, the replacement module, is used for: the target word if it exists judges the target word and the language word
It whether there is N member relationship between the adjacent participle of participle to be replaced in symbol string, wherein participle to be replaced is the language character string
The middle pronunciation participle same or similar with the target word；The N member relationship if it exists, by described in the language character string to
Replacement participle replaces with the language character string after the target word is optimized.
Optionally, the replacement module, is used for: the target word if it exists, judge the target word whether be name,
Name or fuzzy phoneme word；If so, participle corresponding in the language character string is replaced with the language after the target word is optimized
Say character string.
The third aspect, the embodiment of the present invention provide a kind of electronic equipment, include memory and one or one with
On program, one of them perhaps more than one program be stored in memory and be configured to by one or more than one
It includes the instruction for performing the following operation that processor, which executes the one or more programs:
Obtain voice messaging；
Speech recognition is carried out to the voice messaging, obtains the corresponding language character string of the voice messaging；
According to the personalized character database of user in input method, the language character string is optimized after being optimized
Language character string.
Fourth aspect, the embodiment of the present invention provide a kind of computer readable storage medium, are stored thereon with computer program,
The program performs the steps of when being executed by processor
Obtain voice messaging；
Speech recognition is carried out to the voice messaging, obtains the corresponding language character string of the voice messaging；
According to the personalized character database of user in input method, the language character string is optimized after being optimized
Language character string.
Said one or multiple technical solutions in the embodiment of the present application, at least have the following technical effect that
The embodiment of the present application provides a kind of voice information processing method, to speech recognition obtain language character string, according to
The personalized character database of user optimizes it in input method, enable the language character string after optimization more accurately
The personalized character input situation for reflecting user, to further increase the accuracy rate of speech recognition.
Detailed description of the invention
Fig. 1 is a kind of flow diagram of voice information processing method provided by the embodiments of the present application；
Fig. 2 is a kind of block diagram of speech information processing apparatus provided by the embodiments of the present application；
Fig. 3 is the structural schematic diagram of a kind of electronic equipment provided by the embodiments of the present application.
Specific embodiment
In technical solution provided by the embodiments of the present application, by providing a kind of voice information processing method, according to user
Personalized character database, to optimize to the result of speech recognition, the result after the optimization enable is more accurate
The personalized character input situation for reflecting user, to further increase the accuracy rate of speech recognition.
With reference to the accompanying drawing to main realization principle, specific embodiment and its correspondence of the embodiment of the present application technical solution
The beneficial effect that can reach is explained in detail.
Embodiment
Referring to FIG. 1, the embodiment of the present application provides a kind of voice information processing method, this method comprises:
S110: voice messaging is obtained；
S120: speech recognition is carried out to the voice messaging, obtains the corresponding language character string of the voice messaging；
S130: according to the personalized character database of user in input method, acquisition is optimized to the language character string
Language character string after optimization.
In specific implementation process, when user inputs text by voice, S110 can be executed and obtain electronic equipment
The collected voice messaging of voice acquisition device such as microphone.When user carries out text conversion to the voice messaging in application program
When operation, S110 can also be executed and obtain the voice messaging that user requests conversion, the embodiment of the present application does not limit voice messaging
Acquisition modes.
After S110, executes S120 and speech recognition is carried out to the voice messaging got.Hidden Ma Er can specifically be used
Can the methods of husband's model, vector quantization, artificial neural network carry out speech recognition, identification obtains the corresponding language word of voice messaging
Symbol string.The language character string obtained for identification further executes S130, according to the personalized character data of user in input method
Library optimizes it.
Specifically, in order to optimize to language recognition result, of user is directed to by input method for the embodiment of the present application
Property input condition construct personalized character database.The personalization character database is used to store the spy in user's input process
Levy character data.Wherein, the characteristic character data of user include: the fuzzy phoneme word of user, name, place name, N member relative, from
Defined terms, high frequency words etc..Fuzzy phoneme word is mispronounced for user's habituation and/or wrong defeated corresponding upper screen word, such as: assuming that user is
One " H ", " F " regardless of fuzzy phoneme user, when user inputs " feihuang ", what is shielded in selection is fuzzy phoneme
" huihuang " corresponding " splendidness ", then " splendidness " is then the fuzzy phoneme word of the user.N member relative is two that association occurs
A or multiple words, such as: user often inputs " I likes closing ", i.e., " likes " being often associated with appearance with " closing ", then " happiness
Vigorously "+" closing " has binary crelation, if " liking closing quiet " often association occurs, then " liking "+" closing "+" quiet
It is quiet " there is ternary relation.
The personalized character database of user can be established by following one or more modes:
Mode one obtains name and/place name that user inputs in default application program；According to the name of acquisition and/or
Place name establishs or updates the personalized character database of user.Wherein, default application program includes: map class application program is led to
Interrogate record, memorandum, instant communication software etc..Map class application program include digital map navigation software, taxi-hailing software, software of riding,
Tourism software etc..Name, place name usually will appear special layout speech recognition to obtain result often inaccurate, such as: voice
The language character string that " liming " speech recognition obtains often is " Li Ming ", but what user actually wanted to input is in address list
" standing bright ".User is written into the name inputted in user communication record, map class application program, instant communication software and/place name
Personalized character database, speech recognition result is optimized according to the individuation data library, is able to solve language in the prior art
Sound identifies the technical problem lower to name or place name identification accuracy rate.
Mode two obtains user by the fuzzy phoneme word of screen in input method (determining input), and/or, it obtains user and exists
Input number is greater than the high frequency words of the first given threshold in preset period of time；According to the fuzzy phoneme word and/or high frequency words of acquisition,
Establish or update the personalized character database of user.For fuzzy phoneme word, in the personalized word that fuzzy phoneme word is written to user
When according in database, also the corresponding input pronunciation of fuzzy phoneme word is written in personalized character database.Such as: user's input
" shengfen ", due to the fuzzy phoneme user that the user is " eng " and " en ", the corresponding candidate item provided of input method includes
" province ", " identity ", finally the upper word shielded is " identity " to user, then by " identity " as the user fuzzy phoneme word,
" shengfen " is written in the personalized character database of user together as the input pronunciation of " identity ".It include mould by establishing
The user individual character database for pasting sound word, the identification that can greatly improve true, the inapt voice messaging of cacoepy are quasi-
True rate solves in the prior art to the technical problem of fuzzy phoneme identification inaccuracy.
Mode three obtains N number of input word that user continuously inputs, and N is the integer more than or equal to two；Judge this N obtained
Whether the input number of a input word is more than or equal to the second given threshold；If the input number of this N number of input word is more than or equal to the
Two given thresholds, it is believed that there is N member relationship, using this N number of input word as N member relative, and according to this between this N number of input word
N member relative establishs or updates the personalized character database of user；Conversely, being then not considered as have N former between this N number of input word
Relationship.Such as: assuming that user continuously input N number of input word " liking ", " Fei Teng ", " sound " input number (i.e. N number of word
Contact the number occurred) it is greater than the second given threshold, it is considered that " liking "+" Fei Teng "+" sound " have ternary relation, it will
In its personalized character database that user is written.
When establishing personalized character database, a User ID can be established for each user, continuous study is each
User ID corresponds to the personalized input behavior of user, the number in personalized character database constantly to update each user
According to.When optimizing to speech recognition result, the corresponding user of the i.e. identified voice messaging of the speech recognition object is obtained
ID, and then the corresponding personalized character database of the User ID is obtained, to be optimized according to the personalized character database of itself
The speech recognition result of its voice messaging.
When establishing personalized character database by above-mentioned one or more modes, client can be stored it in,
Cloud can also be stored it in, the embodiment of the present application is not intended to limit its storage location.Based on established personalized number of characters
According to library, S130 is continued to execute after S120.S130 can obtain the corresponding User ID of S130, be somebody's turn to do from client or cloud
The corresponding personalized character database of User ID carries out the language character string that identification obtains according to the personalization character database
Optimization, the language character string after being optimized.
When being optimized according to personalized character database to language character string, specifically first language character string can be carried out
Participle；Then, judge in personalized character database with the presence or absence of same or similar with participle pronunciation any in word segmentation result
Target word；Participle corresponding in language character string is replaced with the language character after target word is optimized by the target word if it exists
String；Conversely, the target word then abandons this suboptimization if it does not exist.Wherein, discrimination is lower than default recognition threshold when speech recognition
Two pronunciations may be considered that pronunciation is close, such as: assuming that the discrimination of " l " and " n " are lower than default identification threshold when speech recognition
Value, then " l " and " n " pronunciation is close；And/or the fuzzy phoneme of user is considered that pronunciation is close, and such as: assuming that user's is fuzzy
Sound is " in " and " ing ", it is considered that " in " and " ing " pronunciation is close.
When there is the target word same or similar with the pronunciation segmented in language character string in personalized character database,
Participle to be replaced that can be directly same or similar with target word with pronunciation in the target word alternate language character string.Such as: it is false
If the language character string that speech recognition obtains is " I likes the sound of boiling ", " I likes the sound of boiling " is segmented,
" I ", " liking ", " boiling ", " sound " are segmented, then the user individual character by each participle in input method
It carries out searching in database and judges whether there is the same or similar target word of pronunciation, judge to exist identical as " boiling " pronunciation
Target word " Fei Teng ", then " boiling " is replaced with the language character string after " Fei Teng " is optimized, " I likes the sound risen of expense
Sound ".
When there is the target word same or similar with the pronunciation segmented in language character string in personalized character database,
It can also further judge whether the target word meets replacement policy, replacement operation is executed if meeting replacement policy, is otherwise put
Abandon replacement operation.The replacement policy includes: that target word meets N member relationship；Target word is preset kind such as name, ground, obscures
The words such as sound, user's custom words；Target word and current application environment match.
Specifically, judging to close between the adjacent participle of participle to be replaced with the presence or absence of N member in target word and language character string
System；Participle to be replaced in language character string is replaced with the language character string after target word is optimized by N member relationship if it exists；
N member relationship if it does not exist continues the judgement of other replacement policies or abandons this sub-optimal operation.Such as: judging individual character
When changing in character database in the presence of target word " Fei Teng " identical with participle " boiling " pronunciation in language character string, further sentence
Whether with N member relationship between the adjacent participle " liking " of disconnected " Fei Teng " and " boiling " and/or " sound ", according to personalized word
N member relative in symbol database judges that " liking "+" Fei Teng "+" sound " has ternary relation, i.e. target word " Fei Teng "
Meet replacement policy, then " boiling " is replaced with " Fei Teng ".The suitable target word that can be directed to of the strategy is personalized number of characters
Progress according to N member relative and high frequency words in library further judges, to guarantee the accuracy of optimization.
It is often the smallest vocabulary of change rate for name, place name, fuzzy phoneme word etc., but is also not easy to be identified.Judging
There are when target word in personalized database out, it can be determined that whether the target word is the default classes such as name, place name, fuzzy phoneme word
The vocabulary of type；If so, participle to be replaced is replaced with target word, conversely, continuing the judgement of other replacement policies or putting
Abandon this sub-optimal operation.Such as: assuming that " Fei Teng " is the name of the contact person in user communication record, judging personalized character
When there is target word " Fei Teng " identical with participle " boiling " pronunciation in language character string in database, further judge
" Fei Teng " is name, then " boiling " is replaced with " Fei Teng ".
Whether it is replaced, can also judges whether target word matches with current application environment, it will be wait replace if matching
It changes participle and replaces with target word, conversely, then continuing the judgement of other replacement policies or abandoning this sub-optimal operation.Example
Such as: assuming that target word is " Fei Xiang ", current application program is that " XX music " corresponding application environment is " music ", and target word " is taken
The label of Xiang " includes " music ", judges " Fei Xiang " and current application environments match, then participle to be replaced is replaced with target
Word " Fei Xiang ".Conversely, if current application program is that the corresponding application environment of certain Games Software and target word " Fei Xiang " are mismatched, that
It then abandons participle to be replaced replacing with target word.
In specific implementation process, language character string of this specification embodiment also after display optimization after S130.Aobvious
During metacharacter string after showing optimization, it can permit with display optimization information, to prompt this recognition result of user optimised
Family allowable executes the operation for abandoning optimization.If user abandons this suboptimization, the target word being abandoned is obtained, deletes user individual
Target word in character database, to update the personalized character database of user.Pass through the personalized word of user in input method
The continuous renewal of database is accorded with, so that it is more acurrate according to optimization of the personalized character database to speech recognition result, it can more paste
The personalized character input situation of nearly user, to further increase the accuracy rate of speech recognition.
A kind of voice information processing method is provided for above-described embodiment, the embodiment of the present application also correspondence provides a kind of voice
Information processing unit, referring to FIG. 2, the device includes:
Acquiring unit 21 obtains voice messaging；
Recognition unit 22 carries out speech recognition to the voice messaging, obtains the corresponding language character of the voice messaging
String；
Optimize unit 23, for the personalized character database according to user in input method, to the language character string into
The language character string gone after being optimized.
As an alternative embodiment, described device further include: construction unit 24.Construction unit 24 is used for by such as
The personalized character database of user is established, updated to lower a kind of or various ways:
One, the name and/place name that user inputs in default application program are obtained；According to the name and/or place name, build
Found or update the personalized character database.
Two, it obtains the user and passes through the fuzzy phoneme word shielded in input method, and/or, the user is obtained in preset time
Input number is greater than the high frequency words of the first given threshold in period；According to the fuzzy phoneme word and/or the high frequency words, establish or
Update the personalized character database.
Three, N number of input word that user continuously inputs is obtained, N is the integer more than or equal to two；Judge N number of input word
Input number whether be greater than the second given threshold；If so, using N number of input word as N member relative, and according to the N
First relative establishs or updates the personalized character database.
As an alternative embodiment, the optimization unit 23, comprising: word segmentation module, judgment module and replacement mould
Block.Word segmentation module is used for: being segmented to the language character string；Judgment module is used for: judging the personalized character data
With the presence or absence of the target word same or similar with participle pronunciation any in word segmentation result in library；Replacement module is used for: institute if it exists
Target word is stated, participle corresponding in the language character string is replaced with into the language character string after the target word is optimized.
As an alternative embodiment, the replacement module can be used for: the target word if it exists, described in judgement
It whether there is N member relationship in target word and the language character string between the adjacent participle of participle to be replaced, wherein to be replaced point
Word is the participle that pronunciation is same or similar with the target word in the language character string；The N member relationship if it exists, will be described
To be replaced segment described in language character string replaces with the language character string after the target word is optimized.The replacement module
Can be used for: the target word if it exists judges whether the target word is name, place name or fuzzy phoneme word；If so, will
Corresponding participle replaces with the language character string after the target word is optimized in the language character string.
About the device in above-described embodiment, wherein modules execute the concrete mode of operation in related this method
Embodiment in be described in detail, no detailed explanation will be given here.
Fig. 3 is a kind of electronic equipment for realizing voice information processing method shown according to an exemplary embodiment
800 block diagram.For example, electronic equipment 800 can be mobile phone, computer, digital broadcasting terminal, messaging device, trip
Play console, tablet device, Medical Devices, body-building equipment, personal digital assistant etc..
Referring to Fig. 3, electronic equipment 800 may include following one or more components: processing component 802, memory 804,
Power supply module 806, multimedia component 808, audio component 810 input/show the interface 812 of (I/O), sensor module 814,
And communication component 816.
The integrated operation of the usual controlling electronic devices 800 of processing component 802, such as with display, call, data are logical
Letter, camera operation and record operate associated operation.Processing element 802 may include one or more processors 820 to hold
Row instruction, to perform all or part of the steps of the methods described above.In addition, processing component 802 may include one or more moulds
Block, convenient for the interaction between processing component 802 and other assemblies.For example, processing component 802 may include multi-media module, with
Facilitate the interaction between multimedia component 808 and processing component 802.
Memory 804 is configured as storing various types of data to support the operation in equipment 800.These data are shown
Example includes the instruction of any application or method for operating on electronic equipment 800, contact data, telephone directory number
According to, message, picture, video etc..Memory 804 can by any kind of volatibility or non-volatile memory device or they
Combination realize, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM) is erasable
Programmable read only memory (EPROM), programmable read only memory (PROM), read-only memory (ROM), magnetic memory, quick flashing
Memory, disk or CD.
Power supply module 806 provides electric power for the various assemblies of electronic equipment 800.Power supply module 806 may include power supply pipe
Reason system, one or more power supplys and other with for electronic equipment 800 generate, manage, and distribute the associated component of electric power.
Multimedia component 808 includes the screen that offer one between the electronic equipment 800 and user shows interface.
In some embodiments, screen may include liquid crystal display (LCD) and touch panel (TP).If screen includes touch surface
Plate, screen may be implemented as touch screen, to receive input signal from the user.Touch panel includes one or more touches
Sensor is to sense the gesture on touch, slide, and touch panel.The touch sensor can not only sense touch or sliding
The boundary of movement, but also detect duration and pressure associated with the touch or slide operation.In some embodiments,
Multimedia component 808 includes a front camera and/or rear camera.When equipment 800 is in operation mode, as shot mould
When formula or video mode, front camera and/or rear camera can receive external multi-medium data.Each preposition camera shooting
Head and rear camera can be a fixed optical lens system or have focusing and optical zoom capabilities.
Audio component 810 is configured as showing and/or input audio signal.For example, audio component 810 includes a Mike
Wind (MIC), when electronic equipment 800 is in operation mode, when such as call mode, recording mode, and voice recognition mode, microphone
It is configured as receiving external audio signal.The received audio signal can be further stored in memory 804 or via logical
Believe that component 816 is sent.In some embodiments, audio component 810 further includes a loudspeaker, for showing audio signal.
I/O interface 812 provides interface between processing component 802 and peripheral interface module, and above-mentioned peripheral interface module can
To be keyboard, click wheel, button etc..These buttons may include, but are not limited to: home button, volume button, start button and lock
Determine button.
Sensor module 814 includes one or more sensors, for providing the state of various aspects for electronic equipment 800
Assessment.For example, sensor module 814 can detecte the state that opens/closes of equipment 800, the relative positioning of component, such as institute
The display and keypad that component is electronic equipment 800 are stated, sensor module 814 can also detect electronic equipment 800 or electronics
The position change of 800 1 components of equipment, the existence or non-existence that user contacts with electronic equipment 800,800 orientation of electronic equipment
Or the temperature change of acceleration/deceleration and electronic equipment 800.Sensor module 814 may include proximity sensor, be configured to
It detects the presence of nearby objects without any physical contact.Sensor module 814 can also include optical sensor, such as
CMOS or ccd image sensor, for being used in imaging applications.In some embodiments, which can be with
Including acceleration transducer, gyro sensor, Magnetic Sensor, pressure sensor or temperature sensor.
Communication component 816 is configured to facilitate the communication of wired or wireless way between electronic equipment 800 and other equipment.
Electronic equipment 800 can access the wireless network based on communication standard, such as WiFi, 2G or 3G or their combination.Show at one
In example property embodiment, communication component 816 receives broadcast singal or broadcast from external broadcasting management system via broadcast channel
Relevant information.In one exemplary embodiment, the communication component 816 further includes near-field communication (NFC) module, short to promote
Cheng Tongxin.For example, radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra wide band can be based in NFC module
(UWB) technology, bluetooth (BT) technology and other technologies are realized.
In the exemplary embodiment, electronic equipment 800 can be by one or more application specific integrated circuit (ASIC), number
Word signal processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field programmable gate array
(FPGA), controller, microcontroller, microprocessor or other electronic components are realized, for executing the above method.
In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instruction, example are additionally provided
It such as include the memory 804 of instruction, above-metioned instruction can be executed by the processor 820 of electronic equipment 800 to complete the above method.Example
Such as, the non-transitorycomputer readable storage medium can be ROM, random access memory (RAM), CD-ROM, tape, soft
Disk and optical data storage devices etc..
A kind of non-transitorycomputer readable storage medium, when the instruction in the storage medium is by the processing of mobile terminal
When device executes, so that mobile terminal is able to carry out a kind of voice information processing method, which comprises obtain voice messaging；
Speech recognition is carried out to the voice messaging, obtains the corresponding language character string of the voice messaging；According to user in input method
Personalized character database, the language character string after being optimized is optimized to the language character string.
Fig. 3 is the structural schematic diagram of server in the embodiment of the present invention.The server 1900 can be different because of configuration or performance
And generate bigger difference, may include one or more central processing units (central processing units,
CPU) 1922 (for example, one or more processors) and memory 1932, one or more storage application programs
1942 or data 1944 storage medium 1930 (such as one or more mass memory units).Wherein, memory 1932
It can be of short duration storage or persistent storage with storage medium 1930.Be stored in storage medium 1930 program may include one or
More than one module (diagram does not mark), each module may include to the series of instructions operation in server.Further
Ground, central processing unit 1922 can be set to communicate with storage medium 1930, and storage medium 1930 is executed on server 1900
In series of instructions operation.
Server 1900 can also include one or more power supplys 1926, one or more wired or wireless nets
Network interface 1950, one or more inputs show interface 1958, one or more keyboards 1956, and/or, one or
More than one operating system 1941, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM
Etc..
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to of the invention its
Its embodiment.This application is intended to cover any variations, uses, or adaptations of the invention, these modifications, purposes or
Person's adaptive change follows general principle of the invention and including the undocumented common knowledge in the art of the disclosure
Or conventional techniques.The description and examples are only to be considered as illustrative, and true scope and spirit of the invention are by following
Claim is pointed out.
It should be understood that the present invention is not limited to the precise structure already described above and shown in the accompanying drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present invention is limited only by the attached claims
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all in spirit of the invention and
Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of voice information processing method, which is characterized in that the described method includes:
Obtain voice messaging；
Speech recognition is carried out to the voice messaging, obtains the corresponding language character string of the voice messaging；
According to the personalized character database of user in input method, the language after being optimized is optimized to the language character string
Say character string.
2. the method as described in claim 1, which is characterized in that the described method includes:
Obtain the name and/place name that user inputs in default application program；
According to the name and/or place name, the personalized character database is establishd or updated.
3. the method as described in claim 1, which is characterized in that the method also includes:
It obtains the user and passes through the fuzzy phoneme word shielded in input method, and/or, it is defeated in preset period of time to obtain the user
Indegree is greater than the high frequency words of the first given threshold；
According to the fuzzy phoneme word and/or the high frequency words, the personalized character database is establishd or updated.
4. the method as described in claim 1, which is characterized in that the method also includes:
N number of input word that user continuously inputs is obtained, N is the integer more than or equal to two；
Judge whether the input number of N number of input word is greater than the second given threshold；
If so, using N number of input word as N member relative, and the personalization is establishd or updated according to the N member relative
Character database.
5. the method as described in Claims 1 to 4 is any, which is characterized in that according to the personalized number of characters of user in input method
According to library, the language character string after being optimized is optimized to the language character string, comprising:
The language character string is segmented；
Judge in the personalized character database with the presence or absence of the mesh same or similar with participle pronunciation any in word segmentation result
Mark word；
Participle corresponding in the language character string is replaced with the language after the target word is optimized by the target word if it exists
Say character string.
6. method as claimed in claim 5, which is characterized in that the target word if it exists, it will be right in the language character string
It should segment and replace with the language character string after the target word is optimized, comprising:
The target word if it exists judges in the target word and the language character string between the adjacent participle of participle to be replaced
With the presence or absence of N member relationship, wherein participle to be replaced is that pronunciation is same or similar with the target word in the language character string
Participle；
It is excellent to be replaced with the target word acquisition by the N member relationship if it exists for participle to be replaced described in the language character string
Language character string after change.
7. method as claimed in claim 5, which is characterized in that the target word if it exists, it will be right in the language character string
It should segment and replace with the language character string after the target word is optimized, comprising:
The target word if it exists judges whether the target word is name, place name or fuzzy phoneme word；
If so, participle corresponding in the language character string is replaced with the language character string after the target word is optimized.
8. a kind of speech information processing apparatus, which is characterized in that described device includes:
Acquiring unit obtains voice messaging；
Recognition unit carries out speech recognition to the voice messaging, obtains the corresponding language character string of the voice messaging；
Optimization unit optimizes the language character string for the personalized character database according to user in input method
Language character string after being optimized.
9. a kind of electronic equipment, which is characterized in that include memory and one or more than one program, wherein one
A perhaps more than one program is stored in memory and is configured to execute described one by one or more than one processor
A or more than one program includes the instruction for performing the following operation:
Obtain voice messaging；
Speech recognition is carried out to the voice messaging, obtains the corresponding language character string of the voice messaging；
According to the personalized character database of user in input method, the language after being optimized is optimized to the language character string
Say character string.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
It is performed the steps of when execution
Obtain voice messaging；
Speech recognition is carried out to the voice messaging, obtains the corresponding language character string of the voice messaging；
According to the personalized character database of user in input method, the language after being optimized is optimized to the language character string
Say character string.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711404260.5A CN109961791B (en) | 2017-12-22 | 2017-12-22 | Voice information processing method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711404260.5A CN109961791B (en) | 2017-12-22 | 2017-12-22 | Voice information processing method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109961791A true CN109961791A (en) | 2019-07-02 |
| CN109961791B CN109961791B (en) | 2021-10-22 |
Family
ID=67019207
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711404260.5A Active CN109961791B (en) | 2017-12-22 | 2017-12-22 | Voice information processing method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109961791B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111564157A (en) * | 2020-03-18 | 2020-08-21 | 浙江省北大信息技术高等研究院 | Conference record optimization method, device, equipment and storage medium |
| CN111627438A (en) * | 2020-05-21 | 2020-09-04 | 四川虹美智能科技有限公司 | Voice recognition method and device |
| CN111737541A (en) * | 2020-06-30 | 2020-10-02 | 湖北亿咖通科技有限公司 | Semantic recognition and evaluation method supporting multiple languages |
| CN112363631A (en) * | 2019-07-24 | 2021-02-12 | 北京搜狗科技发展有限公司 | Input method, input device and input device |
| CN112908337A (en) * | 2021-01-31 | 2021-06-04 | 云知声智能科技股份有限公司 | Method, device and equipment for displaying voice recognition text and storage medium |
| CN113138674A (en) * | 2020-01-19 | 2021-07-20 | 北京搜狗科技发展有限公司 | Input method and related device |
| CN113515618A (en) * | 2020-04-09 | 2021-10-19 | 北京搜狗科技发展有限公司 | Speech processing method, device and medium |
| CN113571055A (en) * | 2020-04-29 | 2021-10-29 | 顾家家居股份有限公司 | Intelligent voice sofa control system |
| CN114357979A (en) * | 2021-12-31 | 2022-04-15 | 科大讯飞股份有限公司 | Subtitle making method and device and computer readable storage medium |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101013443A (en) * | 2007-02-13 | 2007-08-08 | 北京搜狗科技发展有限公司 | Intelligent word input method and input method system and updating method thereof |
| CN101290632A (en) * | 2008-05-30 | 2008-10-22 | 北京搜狗科技发展有限公司 | Input method for user words participating in intelligent word-making and input method system |
| CN101847159A (en) * | 2010-05-11 | 2010-09-29 | 中兴通讯股份有限公司 | Terminal equipment and method for updating word stock thereof |
| CN102270048A (en) * | 2010-06-03 | 2011-12-07 | 北京搜狗科技发展有限公司 | Noun input method and system |
| US20120310643A1 (en) * | 2011-05-23 | 2012-12-06 | Nuance Communications, Inc. | Methods and apparatus for proofing of a text input |
| CN103399890A (en) * | 2013-07-22 | 2013-11-20 | 百度在线网络技术（北京）有限公司 | Method and equipment for collecting words on input method client side |
| CN103578469A (en) * | 2012-08-08 | 2014-02-12 | 百度在线网络技术（北京）有限公司 | Method and device for showing voice recognition result |
| CN103699530A (en) * | 2012-09-27 | 2014-04-02 | 百度在线网络技术（北京）有限公司 | Method and equipment for inputting texts in target application according to voice input information |
| WO2014176959A1 (en) * | 2013-04-28 | 2014-11-06 | 百度在线网络技术（北京）有限公司 | Method and device for providing input candidate entry based on local lexicon |
| CN105206274A (en) * | 2015-10-30 | 2015-12-30 | 北京奇艺世纪科技有限公司 | Voice recognition post-processing method and device as well as voice recognition system |
| US20160027437A1 (en) * | 2014-07-28 | 2016-01-28 | Samsung Electronics Co., Ltd. | Method and apparatus for speech recognition and generation of speech recognition engine |
| CN105632499A (en) * | 2014-10-31 | 2016-06-01 | 株式会社东芝 | Method and device for optimizing voice recognition result |
| CN106527756A (en) * | 2016-10-26 | 2017-03-22 | 长沙军鸽软件有限公司 | Method and device for intelligently correcting input information |
| CN106527757A (en) * | 2016-10-28 | 2017-03-22 | 上海智臻智能网络科技股份有限公司 | Input error correction method and apparatus |
| US20170154034A1 (en) * | 2015-11-26 | 2017-06-01 | Le Holdings (Beijing) Co., Ltd. | Method and device for screening effective entries of pronouncing dictionary |
| CN107169067A (en) * | 2017-05-05 | 2017-09-15 | 上海明数数字出版科技有限公司 | The dictionary picking up method and system of a kind of utilization speech polling Chinese character |
| CN107451121A (en) * | 2017-08-03 | 2017-12-08 | 京东方科技集团股份有限公司 | A kind of audio recognition method and its device |
-
2017
- 2017-12-22 CN CN201711404260.5A patent/CN109961791B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101013443A (en) * | 2007-02-13 | 2007-08-08 | 北京搜狗科技发展有限公司 | Intelligent word input method and input method system and updating method thereof |
| CN101290632A (en) * | 2008-05-30 | 2008-10-22 | 北京搜狗科技发展有限公司 | Input method for user words participating in intelligent word-making and input method system |
| CN101847159A (en) * | 2010-05-11 | 2010-09-29 | 中兴通讯股份有限公司 | Terminal equipment and method for updating word stock thereof |
| CN102270048A (en) * | 2010-06-03 | 2011-12-07 | 北京搜狗科技发展有限公司 | Noun input method and system |
| US20120310643A1 (en) * | 2011-05-23 | 2012-12-06 | Nuance Communications, Inc. | Methods and apparatus for proofing of a text input |
| CN103578469A (en) * | 2012-08-08 | 2014-02-12 | 百度在线网络技术（北京）有限公司 | Method and device for showing voice recognition result |
| CN103699530A (en) * | 2012-09-27 | 2014-04-02 | 百度在线网络技术（北京）有限公司 | Method and equipment for inputting texts in target application according to voice input information |
| WO2014176959A1 (en) * | 2013-04-28 | 2014-11-06 | 百度在线网络技术（北京）有限公司 | Method and device for providing input candidate entry based on local lexicon |
| CN103399890A (en) * | 2013-07-22 | 2013-11-20 | 百度在线网络技术（北京）有限公司 | Method and equipment for collecting words on input method client side |
| US20160027437A1 (en) * | 2014-07-28 | 2016-01-28 | Samsung Electronics Co., Ltd. | Method and apparatus for speech recognition and generation of speech recognition engine |
| CN105632499A (en) * | 2014-10-31 | 2016-06-01 | 株式会社东芝 | Method and device for optimizing voice recognition result |
| CN105206274A (en) * | 2015-10-30 | 2015-12-30 | 北京奇艺世纪科技有限公司 | Voice recognition post-processing method and device as well as voice recognition system |
| US20170154034A1 (en) * | 2015-11-26 | 2017-06-01 | Le Holdings (Beijing) Co., Ltd. | Method and device for screening effective entries of pronouncing dictionary |
| CN106527756A (en) * | 2016-10-26 | 2017-03-22 | 长沙军鸽软件有限公司 | Method and device for intelligently correcting input information |
| CN106527757A (en) * | 2016-10-28 | 2017-03-22 | 上海智臻智能网络科技股份有限公司 | Input error correction method and apparatus |
| CN107169067A (en) * | 2017-05-05 | 2017-09-15 | 上海明数数字出版科技有限公司 | The dictionary picking up method and system of a kind of utilization speech polling Chinese character |
| CN107451121A (en) * | 2017-08-03 | 2017-12-08 | 京东方科技集团股份有限公司 | A kind of audio recognition method and its device |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112363631A (en) * | 2019-07-24 | 2021-02-12 | 北京搜狗科技发展有限公司 | Input method, input device and input device |
| CN113138674A (en) * | 2020-01-19 | 2021-07-20 | 北京搜狗科技发展有限公司 | Input method and related device |
| CN111564157A (en) * | 2020-03-18 | 2020-08-21 | 浙江省北大信息技术高等研究院 | Conference record optimization method, device, equipment and storage medium |
| CN113515618A (en) * | 2020-04-09 | 2021-10-19 | 北京搜狗科技发展有限公司 | Speech processing method, device and medium |
| CN113515618B (en) * | 2020-04-09 | 2024-12-20 | 北京搜狗科技发展有限公司 | Voice processing method, device and medium |
| CN113571055A (en) * | 2020-04-29 | 2021-10-29 | 顾家家居股份有限公司 | Intelligent voice sofa control system |
| CN111627438A (en) * | 2020-05-21 | 2020-09-04 | 四川虹美智能科技有限公司 | Voice recognition method and device |
| CN111737541A (en) * | 2020-06-30 | 2020-10-02 | 湖北亿咖通科技有限公司 | Semantic recognition and evaluation method supporting multiple languages |
| CN112908337A (en) * | 2021-01-31 | 2021-06-04 | 云知声智能科技股份有限公司 | Method, device and equipment for displaying voice recognition text and storage medium |
| CN114357979A (en) * | 2021-12-31 | 2022-04-15 | 科大讯飞股份有限公司 | Subtitle making method and device and computer readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109961791B (en) | 2021-10-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109961791A (en) | A kind of voice information processing method, device and electronic equipment | |
| CN107102746B (en) | Candidate word generation method and device and candidate word generation device | |
| CN105489220B (en) | Speech recognition method and device | |
| CN107992812A (en) | A kind of lip reading recognition methods and device | |
| CN105260360B (en) | Name recognition methods and the device of entity | |
| CN109819288A (en) | Determination method, apparatus, electronic equipment and the storage medium of advertisement dispensing video | |
| CN111831806A (en) | Semantic integrity determination method and device, electronic equipment and storage medium | |
| CN111210844A (en) | Method, device and equipment for determining speech emotion recognition model and storage medium | |
| CN110110207A (en) | A kind of information recommendation method, device and electronic equipment | |
| CN109886211A (en) | Data mask method, device, electronic equipment and storage medium | |
| CN110968246A (en) | Intelligent Chinese handwriting input recognition method and device | |
| CN110858099B (en) | Candidate word generation method and device | |
| CN111381685B (en) | A sentence association method and device | |
| CN108573706A (en) | A kind of audio recognition method, device and equipment | |
| CN112130839A (en) | Method for constructing database, method for voice programming and related device | |
| CN110908523B (en) | Input method and device | |
| CN108241438B (en) | Input method, input device and input device | |
| CN108628461A (en) | A kind of input method and device, a kind of method and apparatus of update dictionary | |
| CN113919293B (en) | Training method and device for formula recognition model | |
| CN112784151A (en) | Method and related device for determining recommendation information | |
| CN112331194A (en) | Input method and device and electronic equipment | |
| CN112363631A (en) | Input method, input device and input device | |
| CN112306251A (en) | An input method, device and device for input | |
| CN109144286A (en) | A kind of input method and device | |
| CN109426354A (en) | A kind of input method, device and the device for input |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |